Papers › UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning

UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning

20 Nov 2022arXiv:2211.10986archive 2025-07-28

Zengzhi Wang, Rui Xia, Jianfei Yu

Aspect-Based Sentiment Analysis (ABSA) aims to provide fine-grained aspect-level sentiment information. There are many ABSA tasks, and the current dominant paradigm is to train task-specific models for each task. However, application scenarios of ABSA tasks are often diverse. This solution usually requires a large amount of labeled data from each task to perform excellently. These dedicated models are separately trained and separately predicted, ignoring the relationship between tasks. To tackle these issues, we present UnifiedABSA, a general-purpose ABSA framework based on multi-task instruction tuning, which can uniformly model various tasks and capture the inter-task dependency with multi-task learning. Extensive experiments on two benchmark datasets show that UnifiedABSA can significantly outperform dedicated models on 11 ABSA tasks and show its superiority in terms of data efficiency.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Aspect ExtractionAspect Sentiment Triplet ExtractionAspect Term Extraction and Sentiment ClassificationAspect-Based Sentiment AnalysisAspect-Based Sentiment Analysis (ABSA)Aspect-Category-Opinion-Sentiment Quadruple ExtractionAspect-oriented Opinion ExtractionMulti-Task LearningSentiment Analysis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Aspect-Based Sentiment Analysis (ABSA) ACOS UnifiedABSA (multi-task) F1 (Laptop) 42.58 #5 of 9 Archive leaderboard report
Aspect-Based Sentiment Analysis (ABSA) ACOS UnifiedABSA (multi-task) F1 (Restaurant) 60.60 #5 of 9 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AdafactorAttentionAttention DropoutBPEDense ConnectionsDropoutGated Linear UnitInverse Square Root ScheduleLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSentencePieceSoftmaxT5

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections